3

According to the TensorFlow webpage at (https://www.tensorflow.org/versions/r1.3/programmers_guide/datasets), the tf.read_file can be used to load an image file from a given filename, and convert it to a Tensor:

image_string = tf.read_file(filename)
image_decoded = tf.image.decode_image(image_string)

In my case however, I want to load a NumPy array rather than an image. So the filename above points to a NumPy array on my machine.

If I were to use tf.read_file(filename) on this filename, then according to the documentation, this function returns a string Tensor (a byte array). How can I convert this into a Tensor representing the data in the NumPy array? Is there an equivalent function to tf.image.decode_image() for decoding a NumPy array?

Karnivaurus
  • 22,823
  • 57
  • 147
  • 247
  • Possible duplicate of [Feeding .npy (numpy files) into tensorflow data pipeline](https://stackoverflow.com/questions/48889482/feeding-npy-numpy-files-into-tensorflow-data-pipeline) – Mohan Radhakrishnan Aug 15 '18 at 13:30

0 Answers0